INDEX

Explanations

references to state-related political or legal issues

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.04

1:0.03

2:0.04

3:0.09

4:0.07

5:0.02

6:0.10

7:0.38

8:0.02

9:0.03

10:0.04

11:0.10

Negative Logits

bush

-2.52

stocks

-2.33

 Fields

-2.27

Var

-2.08

Street

-2.06

 Markets

-2.03

 Sett

-2.01

 Robb

-1.94

 Grounds

-1.94

 Portug

-1.93

POSITIVE LOGITS

 Gutenberg

2.39

 Playboy

2.26

keye

2.20

 pornography

2.12

 rehe

2.07

zsche

2.05

kie

2.03

ertodd

2.01

 masturb

2.00

umbnails

1.96

Activations Density 0.143%

references to state-related political or legal issues

No Known Activations